The Rearch Based On Radial Basis Function Neural Network In Voltage Stability Margin Index

Power system voltage collapse is an important factor in power system instability. Because voltage collapse accident can cause great economic loss and bad influence to the society, it becomes an emergent problem to be solved for the security of power system.Margin index is a measurement of power system is reaching voltage collapse. It is an importment index of power system. The existing algorithm of voltage stability margin index aren't perfect such as precision and speed. This article present two methods to count margin index.Firstly a algorithm of improvede Back Propagation (BP) is present to measurement margin index. Clsaaical BP algorithm easy mire down in partial minimum problem. Rapidity of convergence is slowly; But use P-V curve to acquire margin index require neural network algorithm have goodness of fit. The article combine self adapting rate of study speed algorithm and additive momentum algorithm and computer margin index of IEEE5 node system.Function Neural Network (RBFNN) model for voltage stability margin was presented, The Artificial Neural Network has very strong adapting ability and learning ability. Because of its good association, Generalize, analogy and reasoning, it is used in various fields which are nonlinear. In addition, the ratio of convergence and speed are better than BP algorithm. According to the primary characters of power system, the forming method of training samples is analyzed and studied and a network with multi inputs and multi outputs is built. Voltage stability limit is computed easily and paint P-V curve use this model .at the same time , static voltage stability margin index is calculation and Voltage vulnerable node is identified fast.At last the article assessment margin index of IEEE39 node system using RBFNN algorithm.it is a new method of static voltage stability analyzing.